dax: return the partition offset from fs_dax_get_by_bdev

Prepare for the removal of the block_device from the DAX I/O path by
returning the partition offset from fs_dax_get_by_bdev so that the file
systems have it at hand for use during I/O.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Link: https://lore.kernel.org/r/20211129102203.2243509-26-hch@lst.de
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Author: Christoph Hellwig

drivers/dax/super.c

@@ -69,17 +69,20 @@ EXPORT_SYMBOL_GPL(dax_remove_host);
 /**
  * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
  * @bdev: block device to find a dax_device for
+ * @start_off: returns the byte offset into the dax_device that @bdev starts
  */
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off)
 {
 	struct dax_device *dax_dev;
+	u64 part_size;
 	int id;
 
 	if (!blk_queue_dax(bdev->bd_disk->queue))
 		return NULL;
 
-	if ((get_start_sect(bdev) * SECTOR_SIZE) % PAGE_SIZE ||
-	    (bdev_nr_sectors(bdev) * SECTOR_SIZE) % PAGE_SIZE) {
+	*start_off = get_start_sect(bdev) * SECTOR_SIZE;
+	part_size = bdev_nr_sectors(bdev) * SECTOR_SIZE;
+	if (*start_off % PAGE_SIZE || part_size % PAGE_SIZE) {
 		pr_info("%pg: error: unaligned partition for dax\n", bdev);
 		return NULL;
 	}

drivers/md/dm.c

@@ -637,7 +637,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
 			     struct mapped_device *md)
 {
 	struct block_device *bdev;
-
+	u64 part_off;
 	int r;
 
 	BUG_ON(td->dm_dev.bdev);
@@ -653,7 +653,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
 	}
 
 	td->dm_dev.bdev = bdev;
-	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev);
+	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off);
 	return 0;
 }
 

fs/erofs/internal.h

@@ -51,6 +51,7 @@ struct erofs_device_info {
 	char *path;
 	struct block_device *bdev;
 	struct dax_device *dax_dev;
+	u64 dax_part_off;
 
 	u32 blocks;
 	u32 mapped_blkaddr;
@@ -109,6 +110,7 @@ struct erofs_sb_info {
 #endif	/* CONFIG_EROFS_FS_ZIP */
 	struct erofs_dev_context *devs;
 	struct dax_device *dax_dev;
+	u64 dax_part_off;
 	u64 total_blocks;
 	u32 primarydevice_blocks;
 

fs/erofs/super.c

@@ -312,7 +312,7 @@ static int erofs_init_devices(struct super_block *sb,
 			goto err_out;
 		}
 		dif->bdev = bdev;
-		dif->dax_dev = fs_dax_get_by_bdev(bdev);
+		dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off);
 		dif->blocks = le32_to_cpu(dis->blocks);
 		dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr);
 		sbi->total_blocks += dif->blocks;
@@ -644,7 +644,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	sb->s_fs_info = sbi;
 	sbi->opt = ctx->opt;
-	sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
+	sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off);
 	sbi->devs = ctx->devs;
 	ctx->devs = NULL;
 

fs/ext2/ext2.h

@@ -118,6 +118,7 @@ struct ext2_sb_info {
 	spinlock_t s_lock;
 	struct mb_cache *s_ea_block_cache;
 	struct dax_device *s_daxdev;
+	u64 s_dax_part_off;
 };
 
 static inline spinlock_t *

fs/ext2/super.c

@@ -831,7 +831,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_sb_block = sb_block;
-	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
 
 	spin_lock_init(&sbi->s_lock);
 	ret = -EINVAL;

fs/ext4/ext4.h

@@ -1697,6 +1697,7 @@ struct ext4_sb_info {
 	 */
 	struct percpu_rw_semaphore s_writepages_rwsem;
 	struct dax_device *s_daxdev;
+	u64 s_dax_part_off;
 #ifdef CONFIG_EXT4_DEBUG
 	unsigned long s_simulate_fail;
 #endif

fs/ext4/super.c

@@ -3913,7 +3913,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sbi->s_blockgroup_lock)
 		goto out_free_base;
 
-	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
 	sb->s_fs_info = sbi;
 	sbi->s_sb = sb;
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;

fs/xfs/xfs_buf.c

@@ -1945,7 +1945,7 @@ xfs_alloc_buftarg(
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
-	btp->bt_daxdev = fs_dax_get_by_bdev(bdev);
+	btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off);
 
 	/*
 	 * Buffer IO error rate limiting. Limit it to no more than 10 messages

fs/xfs/xfs_buf.h

@@ -89,6 +89,7 @@ typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
 	struct dax_device	*bt_daxdev;
+	u64			bt_dax_part_off;
 	struct xfs_mount	*bt_mount;
 	unsigned int		bt_meta_sectorsize;
 	size_t			bt_meta_sectormask;